© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 1238
    Prev
    Next
    INDEX
    Explanations

    phrases related to the intended use or application of various items or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of usage or applications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ado
    -0.64
     CLSID
    -0.60
     inev
    -0.60
     Consent
    -0.59
     Explan
    -0.57
     Decay
    -0.56
    erous
    -0.53
     certainty
    -0.53
     Pok
    -0.52
     Devi
    -0.52
    POSITIVE LOGITS
     abroad
    0.91
     outdoors
    0.90
     alongside
    0.89
     elsewhere
    0.86
     overseas
    0.86
    outside
    0.81
     indoors
    0.81
    odied
    0.80
     anywhere
    0.76
     among
    0.75
    Activations Density 0.287%

    No Known Activations